Triple
T15584956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mirabeau station |
E374594
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Pont Mirabeau |
E465145
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Pont Mirabeau | Statement: [Mirabeau station, namedAfter, Pont Mirabeau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pont Mirabeau Context triple: [Mirabeau station, namedAfter, Pont Mirabeau]
-
A.
Pont Mirabeau
chosen
Pont Mirabeau is a famous late-19th-century bridge over the Seine in Paris, renowned for its elegant metal arches and its association with Guillaume Apollinaire’s poetry.
-
B.
Fontaine-Française
Fontaine-Française is a commune in eastern France, historically notable as the site of a significant 1595 battle during the French Wars of Religion.
-
C.
Pont Rouelle
Pont Rouelle is a Parisian bridge over the Seine that carries the RER C railway line and links the 15th and 16th arrondissements via the Île aux Cygnes.
-
D.
Pont Bonaparte
Pont Bonaparte is a historic bridge in Lyon, France, spanning the Saône River and linking the Old Town with the central Presqu’île district.
-
E.
Pont Drouin
Pont Drouin is a bridge spanning the Saint-Charles River in Quebec, Canada.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e47971481909e986dd999354628 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4f71e48190a15eb0a2138f083f |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 4:11 a.m.